course/pr_1069/it/chapter1/7.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Modelli sequence-to-sequence&quot;,&quot;local&quot;:&quot;modelli-sequence-to-sequence&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/course/pr_1069/it/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/entry/start.693d748d.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/scheduler.37c15a92.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/singletons.60b4c7a2.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/index.18351ede.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/paths.43b6516c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/entry/app.e9cfd099.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/index.2bf4358c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/nodes/0.bb8a536c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/nodes/10.78b26d40.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/Youtube.1e50a667.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/CourseFloatingBanner.9ff4c771.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/DocNotebookDropdown.efc1fb7c.js">
		<link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/getInferenceSnippets.24b50994.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Modelli sequence-to-sequence&quot;,&quot;local&quot;:&quot;modelli-sequence-to-sequence&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="modelli-sequence-to-sequence" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#modelli-sequence-to-sequence"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Modelli sequence-to-sequence</span></h1>  <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-1-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a>  </div> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/0_4KEb08xrE" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-g17uha">I modelli encoder-decoder (detti anche modelli <em>sequence-to-sequence</em>) utilizzano entrambi i componenti dell’architettura Transformer. Ad ogni passaggio, gli attention layer dell’encoder hanno accesso a tutte le parole della frase iniziale, mentre gli attention layer del decoder possono solo accedere alle parole che precedono linearmente una data parola nell’input.</p> <p data-svelte-h="svelte-nga904">Il pre-addestramento di questi modelli può essere fatto utilizzando gli obiettivi dei modelli encoder o decoder, anche se solitamente include un livello di complessità maggiore. Ad esempio, <a href="https://huggingface.co/t5-base" rel="nofollow">T5</a> è pre-addestrato rimpiazzando porzioni random di testo (che possono contenere più di una parola) con una speciale mask word, con l’obiettivo di predirre il testo rimpiazzato dalla mask word stessa.</p> <p data-svelte-h="svelte-14dplnv">I modelli sequence-to-sequence sono più adatti ai compiti che hanno a che fare con la generazione di nuove frasi sulla base di un input preciso, come il riassunto, la traduzione, o la generazione di risposte a domande.</p> <p data-svelte-h="svelte-fo4740">Tra i rappresentanti di questa famiglia di modelli ci sono:</p> <ul data-svelte-h="svelte-1lyffe"><li><a href="https://huggingface.co/transformers/model_doc/bart.html" rel="nofollow">BART</a></li> <li><a href="https://huggingface.co/transformers/model_doc/mbart.html" rel="nofollow">mBART</a></li> <li><a href="https://huggingface.co/transformers/model_doc/marian.html" rel="nofollow">Marian</a></li> <li><a href="https://huggingface.co/transformers/model_doc/t5.html" rel="nofollow">T5</a></li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/it/chapter1/7.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_u8ez91 = {
						assets: "/docs/course/pr_1069/it",
						base: "/docs/course/pr_1069/it",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/course/pr_1069/it/_app/immutable/entry/start.693d748d.js"),
						import("/docs/course/pr_1069/it/_app/immutable/entry/app.e9cfd099.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 10],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>